Memory Read Reclaim Prioritization for Uncorrectable Error Blocks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in reducing read latency and maintaining data reliability due to uncorrectable errors and read disturbances, especially in non-volatile memory systems used in portable devices.
Innovation Solution
A memory system that utilizes reliability information from pre-read operations to determine pre-victim blocks for read reclaim, prioritizes read reclaim based on error types, and performs pre-read, normal, and internal read reclaims accordingly, with a controller managing the process to optimize data recovery and storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If read reclaim is performed on all victim blocks without priority differentiation, then data reliability is improved, but read latency increases due to unnecessary operations on blocks without uncorrectable errors
Solution Approach 1:
The patent applies local quality by differentiating the treatment of victim blocks based on their error characteristics. Blocks with uncorrectable errors (pre-victim blocks) receive priority read reclaim operations, while blocks without uncorrectable errors receive standard treatment. This selective approach ensures that reliability improvement efforts are concentrated where actually needed, avoiding unnecessary operations on healthy blocks and thus reducing overall read latency.
Solution Approach 2:
The patent implements feedback mechanisms by monitoring and analyzing error information from pre-read operations. The controller uses this feedback to dynamically identify pre-victim blocks and adjust read reclaim priorities accordingly. This closed-loop approach ensures that read reclaim operations are triggered based on actual error conditions rather than uniform scheduling, optimizing both reliability and performance.
2Reliability
If pre-read reclaim is prioritized over normal and internal read reclaims, then uncorrectable errors are addressed faster, but overall productivity decreases due to deferred processing of other victim blocks
Solution Approach 1:
The patent applies dynamics by implementing a flexible, multi-level priority system for read reclaim operations. Instead of a static priority structure, the system dynamically adjusts priorities based on the type of victim block (pre-victim, normal victim, internal victim) and current system conditions. This dynamic prioritization allows the system to respond adaptively to different error scenarios while maintaining overall processing efficiency through balanced resource allocation.
Solution Approach 2:
The patent implements preliminary action by performing pre-read operations to identify blocks with uncorrectable errors before they cause data loss. This advance detection allows the system to proactively schedule read reclaim operations on pre-victim blocks, preventing future read failures. The preliminary identification and prioritization of at-risk blocks enables the system to address potential issues before they impact overall productivity.
3Reliability
If read reclaim operations are performed frequently to prevent uncorrectable errors, then data reliability is enhanced, but energy consumption increases
Solution Approach 1:
The patent applies preliminary anti-action by using pre-read operations to detect and flag blocks with uncorrectable errors before they can cause data loss. This preventive identification allows the system to target read reclaim operations only to blocks that actually need them, rather than performing frequent blanket read reclaim operations on all blocks. By anticipating and addressing problems only where they exist, the system enhances data integrity while minimizing unnecessary energy consumption.
Data Source
AI summary
Disclosed is a memory system including a memory device including a plurality of memory blocks, and a controller suitable for controlling the memory device to perform pre-read reclaim on pre-victim blocks of pre-read blocks among the plurality of memory blocks, the pre-victim blocks including uncorrectable errors, the pre-read blocks being blocks on which a pre-read operation has been performed. The memory system performs read reclaim operations to improve the reliability of non-volatile memory. The controller performs the pre-read operation on sequential data stored in the memory blocks and determines pre-victim blocks based on uncorrectable errors detected during the pre-read operation. The controller reorders the reclaim sequence according to a priority among the pre-read reclaim, a normal read reclaim, and an internal read reclaim. These operations reduce read latency and prevent uncorrectable errors.